**It’s a big problem , why linux on my pc slower 50% than windows?
**
I have already disable ‘AMD Cool Quiet’,and it seemed always work at full speed(3500mHz).
What should i check now? I have try linuxmint live cd just now , same result.
Does it seem odd, or relevant, that the Linux readings have the two L1
memory labels backwards, and are missing tiny things like Northbridge and
Southbridge versions? Maybe it’s just a lack of proper system detection
for the Linux tests, but that seems pretty fundamental.
Otherwise, the numbers seem to fluctuate a lot, I agree. I wonder if
running the tests as ‘root’ would make a difference (I assume you were not
doing that, since normally running things, as ‘root’ is frowned upon
without good reason, particularly in the GUI) if only because ‘root’ is
powerful enough to ignore ulimit things most of the time (or so I think…
maybe unless explicitly stated) where a normal user cannot. I could
imagine, depending on the system’s scheduler, that a system may prioritize
some work above another kind of work in order to give other processes a
chance to use the system despite something deliberately taxing processors
in particular (like a benchmark test).
In my own experience, I’ve had the opposite feeling when switching between
operating systems, so maybe it’s something about your hardware
specifically, though I have no great ideas on what that may be. I’ve used
AMD stuff a lot in the past and it has been great, but recently the newer
systems all have Intel processors.
–
Good luck.
If you find this post helpful and are logged into the web interface,
show your appreciation and click on the star below…
We got a PC running leap which uses the FX-6300 processor. It’s on a gigabyte mb. We find its performance pretty good. Just as a comparison, here are our results.
I’m not sure I ran the tests under the best of conditions btw. I left a flash jigsaw game me mother had been playing open in a browser window (she wanted to return to it) and ran the tests over ssh.
Just one thought. I don’t know if this applies to all AMD 970A boards or just mine but with my Gigabyte one I had issues with Network and USB3. The first advice I found was to set IOMMU to enabled. One of the downsides of this setting was it started spitting out a number of kernel errors and performance dropped.
If you are in a similar situation, use iommu=soft rather than the BIOS setting.
As a more general thought. I would check to see if you are getting a lot of weird kernel errors anyway.
I have try add iommu=soft in the kernel parameters and it work very well.**
Before:
Now:
I think this is a bug with kernel ? i will report this when i’m free.
I have no any problem with Network , but USB3 work with USB2 speed.
There is no additional error message after or before use iommu=soft , Just some warring(I think it’s waring , not error)
0.000000] ACPI: Early table checksum verification disabled 0.000000] ACPI: RSDP 0x00000000000F0490 000024 (v02 ALASKA)
0.000000] ACPI: XSDT 0x00000000CDE6C070 00005C (v01 ALASKA A M I 01072009 AMI 00010013)
0.000000] ACPI: FACP 0x00000000CDE72528 00010C (v05 ALASKA A M I 01072009 AMI 00010013)
0.000000] ACPI BIOS Warning (bug): Optional FADT field Pm2ControlBlock has zero address or length: 0x0000000000000000/0x1 (20150410/tbfadt-654)
0.000000] ACPI: DSDT 0x00000000CDE6C160 0063C2 (v02 ALASKA A M I 00000000 INTL 20051117)
0.000000] ACPI: FACS 0x00000000CDE75080 000040
0.000000] ACPI: APIC 0x00000000CDE72638 00008E (v03 ALASKA A M I 01072009 AMI 00010013)
0.000000] ACPI: FPDT 0x00000000CDE726C8 000044 (v01 ALASKA A M I 01072009 AMI 00010013)
0.000000] ACPI: MCFG 0x00000000CDE72710 00003C (v01 ALASKA A M I 01072009 MSFT 00010013)
0.000000] ACPI: HPET 0x00000000CDE72750 000038 (v01 ALASKA A M I 01072009 AMI 00000005)
0.000000] ACPI: SSDT 0x00000000CDE72788 001158 (v01 AMD POWERNOW 00000001 AMD 00000001)
0.000000] ACPI: IVRS 0x00000000CDE738E0 0000C0 (v01 AMD RD890S 00202031 AMD 00000000)
0.000000] ACPI: Local APIC address 0xfee00000
----
0.316614] mtrr: your CPUs had inconsistent variable MTRR settings
0.316615] mtrr: probably your BIOS does not setup all CPUs.
0.316616] mtrr: corrected configuration.
0.320613] ACPI: Added _OSI(Module Device)
0.320614] ACPI: Added _OSI(Processor Device)
0.320616] ACPI: Added _OSI(3.0 _SCP Extensions)
0.320617] ACPI: Added _OSI(Processor Aggregator Device)
0.322739] ACPI: Executed 2 blocks of module-level executable AML code
0.328722] ACPI: Interpreter enabled
0.328727] ACPI Exception: AE_NOT_FOUND, While evaluating Sleep State \_S1_] (20150410/hwxface-580)
0.328731] ACPI Exception: AE_NOT_FOUND, While evaluating Sleep State \_S2_] (20150410/hwxface-580)
----
17.190456] vboxpci: IOMMU not found (not registered)
**Before i add iommu=soft , it show 'IOMMU found', not 'not found', but i can't find different when use virtualbox**
Pleased to see you at least have a PC running at a reasonable speed. It will need someone more expert than me (not difficult) to go through any remaining bits. I will comment though.
I’m short of USB3 devices but if I plug my SandDisk flash drive in. USB3 port: 83.958230] usb 2-3: new SuperSpeed USB device number 2 using xhci_hcd
USB2 port: 114.767358] usb 4-1: new high-speed USB device number 2 using ehci-pci
So I guess USB3 is working correctly on our similar setup.
–
I do see: 0.000000] ACPI BIOS Warning (bug): Optional FADT field Pm2ControlBlock has zero address or length: 0x0000000000000000/0x1 (20150410/tbfadt-654)